CN114676175A - Road bump point detection method, device, equipment and medium - Google Patents
Road bump point detection method, device, equipment and medium Download PDFInfo
- Publication number
- CN114676175A CN114676175A CN202210297104.8A CN202210297104A CN114676175A CN 114676175 A CN114676175 A CN 114676175A CN 202210297104 A CN202210297104 A CN 202210297104A CN 114676175 A CN114676175 A CN 114676175A
- Authority
- CN
- China
- Prior art keywords
- data
- sensor
- deformation
- time
- difference value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 38
- 238000005070 sampling Methods 0.000 claims abstract description 105
- 238000000034 method Methods 0.000 claims abstract description 55
- 230000008569 process Effects 0.000 claims abstract description 25
- 238000007405 data analysis Methods 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000004140 cleaning Methods 0.000 claims description 19
- 230000001133 acceleration Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 11
- 230000005484 gravity Effects 0.000 claims description 10
- 238000007619 statistical method Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 16
- 238000004891 communication Methods 0.000 description 8
- 238000012795 verification Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012731 temporal analysis Methods 0.000 description 3
- 238000000700 time series analysis Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000011985 exploratory data analysis Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 2
- 241001123248 Arma Species 0.000 description 1
- 230000002547 anomalous effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000006757 chemical reactions by type Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000032258 transport Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2474—Sequence data queries, e.g. querying versioned data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0838—Historical data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Fuzzy Systems (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- Computational Mathematics (AREA)
- Algebra (AREA)
- Game Theory and Decision Science (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
Abstract
The disclosure provides a road bump point detection method, a road bump point detection device, equipment and a medium, and relates to the field of data processing, in particular to the technical field of intelligent traffic. The specific implementation scheme is as follows: acquiring first time sequence data, wherein the first time sequence data is deformation data of each sampling moment acquired by a sensor on a vehicle in the driving process of the vehicle on a road section to be detected; performing time series prediction on the first time series data to obtain second time series data, wherein the second time series data comprise deformation data prediction values corresponding to each sampling moment of the first time series; calculating a difference value between the deformation data corresponding to each sampling moment and a deformation data prediction value; and performing data analysis on the calculated difference value corresponding to each sampling moment, and taking the geographic coordinate corresponding to the sampling moment with the difference value larger than the specified threshold value as a bump point on the road section to be detected. The efficiency of detecting the bump point can be improved under the condition of reducing the detection complexity.
Description
Technical Field
The present disclosure relates to the field of data processing technology, and in particular, to the field of intelligent transportation technology.
Background
When the load-carrying vehicle transports goods, the load-carrying vehicle can pass through some bumpy road sections, the bumpy road sections can influence the driving speed and the driving safety of the load-carrying vehicle, meanwhile, the goods on the load-carrying vehicle can be damaged, in order to avoid the influence of the bumpy road sections on the driving of the load-carrying vehicle, the bumpy road sections need to be avoided when the driving route of the load-carrying vehicle is planned.
Disclosure of Invention
The present disclosure provides a road bump point detection method, apparatus, device and medium.
According to a first aspect of the present disclosure, there is provided a road bump point detection method, comprising:
acquiring first time sequence data, wherein the first time sequence data is deformation data of each sampling moment acquired by a sensor in a vehicle in the driving process of the vehicle on a road section to be detected;
performing time series prediction on the first time series data to obtain second time series data, wherein the second time series data comprise deformation data prediction values corresponding to each sampling moment of the first time series;
calculating a difference value between the deformation data corresponding to each sampling moment and a deformation data prediction value;
and performing data analysis on the calculated difference value corresponding to each sampling moment, and taking the geographic coordinate corresponding to the sampling moment with the difference value larger than the specified threshold value as a bump point on the road section to be detected.
According to a second aspect of the present disclosure, there is provided a road bump point detecting device comprising:
the acquisition module is used for acquiring first time sequence data, wherein the first time sequence data is deformation data of each sampling moment acquired by a sensor in a vehicle in the driving process of the vehicle on a road section to be detected;
the prediction module is used for predicting the time sequence of the first time sequence data to obtain second time sequence data, and the second time sequence data comprises a deformation data prediction value corresponding to each sampling moment of the first time sequence;
the calculation module is used for calculating the difference value between the deformation data corresponding to each sampling moment and the deformation data prediction value;
and the bump point determining module is used for carrying out data analysis on the calculated difference value corresponding to each sampling moment, and taking the geographic coordinate corresponding to the sampling moment with the difference value larger than the specified threshold value as the bump point on the road section to be detected.
According to a third aspect of the present disclosure, there is provided an electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the first aspect.
According to a fourth aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of the first aspect.
According to a fifth aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method of the first aspect described above.
It should be understood that the statements in this section are not intended to identify key or critical features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
fig. 1 is a flowchart of a road bump point detection method provided by an embodiment of the present disclosure;
fig. 2 is an exemplary schematic diagram of line graphs of first time-series data and second time-series data provided by an embodiment of the present disclosure;
FIG. 3 is a flow chart of another method of detecting a bump point in a road provided by an embodiment of the disclosure;
FIG. 4 is an exemplary diagram illustrating a degree of correlation of sensor data provided by an embodiment of the present disclosure;
FIG. 5 is a flow chart of another method of detecting a bump point in a road provided by an embodiment of the disclosure;
fig. 6a is an exemplary schematic diagram of street view verification provided in an embodiment of the present disclosure;
FIG. 6b is an exemplary diagram of another street view check provided in the embodiments of the present disclosure;
FIG. 7 is another exemplary diagram of street view verification provided in an embodiment of the present disclosure;
FIG. 8 is a flowchart of a method for determining a degree of jounce at a point of jounce provided by an embodiment of the present disclosure;
fig. 9 is a schematic structural diagram of a road bump point detection device according to an embodiment of the disclosure;
fig. 10 is a block diagram of an electronic device for implementing the road bump point detection method according to the embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
In the related art, avoidance of bumpy road sections is mainly judged by the experience of a driver of a load-carrying vehicle, but with the increasing complexity of a logistics distribution network, the driver can only avoid a specific small part of bumpy road sections by the experience of the driver.
Therefore, it is necessary to detect the road jolting points of all routes in the logistics distribution network, and mark the positions of the jolting points on each route, and currently, the detection of the road jolting points mainly depends on manually detecting the road segment to be detected on site by using various specialized instruments and devices, for example, a longitudinal section type detector, a reaction type detector, an inertia type detector and other devices are used to detect the road segment to be detected on site, and the process of manually detecting the road jolting points by using the instruments and devices is very complicated and has poor timeliness.
In order to solve the above problem, an embodiment of the present disclosure provides a road bump point detection method, which may be executed by an electronic device, where the electronic device may be a smart phone, a tablet computer, a desktop computer, a server, or the like.
The following describes in detail a road bump point detection method provided by the embodiments of the present disclosure.
As shown in fig. 1, an embodiment of the present disclosure provides a road bump point detection method, including:
s101, acquiring first time series data.
The first time sequence data are deformation data of each sampling moment acquired by a sensor in the vehicle in the driving process of the vehicle on the road section to be detected.
The vehicle is a load-carrying vehicle, and may be a vehicle for carrying goods, such as a truck or a logistics vehicle.
The sampling time is the acquisition time point corresponding to each deformation data in the first time sequence data.
In the embodiment of the disclosure, the road section to be detected is a road section in which bump point detection is required, a sensor in a vehicle can be installed at any position on the vehicle, and the sensor can detect deformation data of the installation position of the sensor.
For example, the sensor in the embodiment of the present disclosure may be a gravity sensor, and specifically may be a deformation sensor, and the deformation sensor may be mounted at an axle portion of a vehicle, and is configured to detect and record deformation data of the axle of the vehicle during driving of the vehicle.
In the embodiment of the present disclosure, the sensor in the vehicle may also be a sensor of an intelligent device in the vehicle, and the sensor of the intelligent device may also acquire deformation data, where the intelligent device may be installed on the vehicle or an intelligent device carried by a person in the vehicle, for example, the intelligent device may be a vehicle-mounted terminal in the vehicle or an intelligent device such as a mobile phone and a tablet computer carried by a person in the vehicle, which is not specifically limited in this embodiment of the present disclosure.
S102, performing time series prediction on the first time series data to obtain second time series data.
The second time series data comprise deformation data predicted values corresponding to each sampling moment of the first time series.
As shown in fig. 2, fig. 2 is an exemplary schematic diagram of time-series data provided by an embodiment of the present disclosure, and fig. 2 includes a line graph of first time-series data and a line graph of second time-series data predicted according to the first time-series data.
In the embodiment of the present disclosure, the first time-series data may be predicted by time-series analysis, where the time-series analysis is a method of predicting data at a next time point by inputting time-related series data, and specifically, the first time-series data may be predicted by a time-series model obtained by unsupervised learning, and the second time-series data may be obtained.
For example, the deformation data in the embodiment of the disclosure is deformation data collected by a sensor installed in a vehicle, the first time series data is time series data with a time length of 60S, one deformation amount corresponds to each second, after the time series data with the time length of 60S is input into a time series model, the time series model can determine a time window, assuming that the time window is 5S, the time series model can predict a deformation amount predicted value of 6S from the time series data with the time length of 60S, the time series data with the time length of 1S to 5S, the time series data with the time length of 2S to 6S predicts a deformation amount predicted value of 7S, and so on, deformation amount predicted values of 6S to 60S in the second time series data can be obtained, optionally, the deformation amount corresponding to 1S to 5S in the first time series can be used as the deformation amount predicted values of 1S to 5S in the second time series, second time-series data including the predicted values of the 1 st to 60 th distortion amounts can be obtained.
In one implementation, when the first time-series data is a stationary sequence, an Autoregressive moving average model (ARMA model) can be selected to predict the first time-series data. When the first time series data is a non-stationary sequence, the first time series data needs to be converted into a stationary sequence, and then prediction is performed, the first time series data can be predicted by using an Autoregressive Integrated Moving Average model (ARIMA model), and the ARIMA model can convert the non-stationary sequence into a stationary sequence through differential operation.
In addition, the parameters of the time series model are determined in a manner that: and calculating through an Akaike Information Criterion (AIC) and a Bayesian Information Criterion (BIC), and selecting a parameter value of the model when the BIC or AIC result is minimum as a parameter of the final model.
S103, calculating a difference value between the deformation data corresponding to each sampling moment and the deformation data prediction value.
In the embodiment of the disclosure, the difference value corresponding to each sampling moment can be obtained by calculating the difference value between the deformation data corresponding to each sampling moment and the deformation data prediction value.
And S104, performing data analysis on the calculated difference value corresponding to each sampling moment, and taking the geographic coordinate corresponding to the sampling moment with the difference value larger than the specified threshold value as a bump point on the road section to be detected.
In the embodiment of the disclosure, when the sensor collects deformation data at the sampling time, the vehicle event data recorder in the vehicle can also collect the geographic coordinates of the position of the vehicle at the sampling time, that is, the longitude and latitude of the position of the vehicle, the electronic device can obtain the geographic coordinates collected by the vehicle event data recorder in the vehicle, and then the geographic coordinates corresponding to the sampling time with the difference value larger than the specified threshold value can be used as the bump point on the road section to be detected.
The specified threshold may be a preset value or a value obtained by performing statistical analysis on the difference corresponding to each sampling time, and a specific method for obtaining the specified threshold by performing statistical analysis on the difference will be described below.
By adopting the embodiment of the disclosure, the first time sequence data is obtained through the sensor, namely the deformation data of each sampling moment in the driving process of the vehicle on the road section to be detected is obtained, the second time sequence data is obtained through prediction based on the first time sequence data, the deformation data prediction value included in the second time sequence data is equivalent to the deformation data of each sampling moment when the vehicle drives on a flat road, and as the difference value between the deformation data when the vehicle drives on a bumpy road and the deformation data when the vehicle drives on a flat road is larger, the data analysis can be carried out on the difference value corresponding to each sampling moment by calculating the difference value between the deformation data corresponding to each sampling moment and the deformation data prediction value, and the geographic coordinate corresponding to the sampling moment with the difference value larger than the specified threshold value is used as the bumping point on the road section to be detected. Therefore, extra equipment is not introduced in the detection process to detect the road on the spot, the realization is simple, and the detection efficiency can be improved.
In an actual service scene, a sensor on a vehicle can acquire sensor data in real time in the driving process of the vehicle, the acquired sensor data may have data which affects determination of a bumpy point, and in order to improve accuracy of detection of the bumpy point, data cleaning needs to be performed on the sensor data, and on the basis, S101 can be specifically implemented as follows:
the method comprises the steps of acquiring sensor data acquired by a sensor on a vehicle in the driving process of the vehicle on a road section to be detected, carrying out data cleaning on the sensor data, and taking deformation data corresponding to each sampling moment after the data cleaning as first time sequence data.
The sensor data comprises time and deformation data with corresponding relation, and the deformation data is gravity acceleration or deformation.
It can be understood that the sensors in the vehicle may collect the deformation data in real time and record each of the collected deformation data and the collection time at which the deformation data is collected.
In the case where the sensor in the vehicle is a vehicle-mounted sensor, the deformation data acquired by the sensor is a deformation amount or a gravitational acceleration.
Under the condition that the sensor in the vehicle is a sensor in intelligent equipment in the vehicle, deformation data acquired by the sensor is gravity acceleration.
When the vehicle runs on the road section to be detected, the acceleration, deceleration or zero speed condition may exist, and the deformation data detected by the sensor changes due to the acceleration or deceleration of the vehicle, so that in order to avoid changing the deformation data generated by the acceleration or deceleration of the vehicle as the deformation data generated when the vehicle passes through a bump point, the deformation data collected by the sensor when the vehicle is accelerated or decelerated needs to be removed, and when the vehicle speed is zero, the vehicle is in a stationary state, and at the moment, the deformation data collected by the sensor needs to be removed.
And because the deformation data can also be greatly changed when the vehicle loads and unloads goods, the deformation data collected by the sensor needs to be removed when the vehicle weight changes greatly.
In view of the above situation that deformation data may greatly change, in the embodiment of the present disclosure, the vehicle weight recorded in real time by the sensor installed in the vehicle may be acquired, and then, a time period in which the vehicle weight changes greatly is acquired, and the deformation data acquired by the sensor in the time period is removed.
The vehicle speed recorded by the automobile data recorder in real time in the vehicle can be acquired, the time interval when the vehicle is accelerated and decelerated and the speed is zero can be acquired, and deformation data acquired by the sensor in the time interval can be removed.
Through the data cleaning process, deformation data collected by the sensor when the vehicle accelerates or decelerates can be eliminated, namely, deformation data change caused by acceleration or deceleration of the vehicle is eliminated, the obtained deformation data change is the deformation data change of the vehicle passing through a bump point, the accuracy of bump point detection is improved, meanwhile, when the vehicle is static and the weight of the vehicle changes greatly, the deformation data collected by the sensor are removed, the follow-up interference on invalid data during first time sequence prediction is reduced, and the prediction accuracy on the first time sequence can be improved.
In another embodiment of the present disclosure, a plurality of sensors may be installed on a vehicle, data that may affect determining a bump point may exist in collected sensor data of the plurality of sensors, and in order to improve accuracy of bump point detection, the collected sensor data may be preprocessed, as shown in fig. 3, where S101 may specifically be implemented as:
and S1011, acquiring sensor data acquired by a plurality of sensors on the vehicle in the driving process of the vehicle on the road section to be detected.
The sensor data comprises time and deformation data with corresponding relation, and the deformation data is gravity acceleration or deformation quantity.
And S1012, respectively performing data cleaning on the sensor data of each sensor.
The data cleaning process is the same as the data cleaning process described in the above embodiments, and is not described herein again.
S1013, based on the similarity between the sensor data of each sensor after the data cleaning, a specified sensor is selected from the plurality of sensors.
In the embodiment of the disclosure, the similarity between each two sensor data of the plurality of sensors may be calculated, and because the data between the sensors having high similarity are similar, in order to reduce the calculation amount, one sensor may be selected from the plurality of sensors having high sensor data similarity as the designated sensor.
As shown in fig. 4, fig. 4 is a thermodynamic diagram obtained by performing similarity calculation on sensor data of 8 sensors, and according to the diagram, the sensor 2, the sensor 3, the sensor 4, the sensor 5, the sensor 6, the sensor 7 and the sensor 8 can be selected as a designated sensor from the sensors 1, 2, 3, 4, 5, 6, 7 and 8.
Optionally, in the embodiment of the present disclosure, a skewness value and a kurtosis value of each sensor data may also be calculated, and if the skewness value and the kurtosis value of the sensor data of a certain sensor are different from those of the sensor data of other sensors by a relatively large amount, the sensor data of the certain sensor may be eliminated, that is, the certain sensor is not used as the designated sensor.
For example, if the sensor a and the sensor B are mounted on one axle of the vehicle and the sensor C and the sensor D are mounted on the other axle of the vehicle, the sensor data of the sensor a can be eliminated if the difference between the skewness value and the kurtosis value of the sensor data of the sensor a and the difference between the skewness value and the kurtosis value of the other sensor data are large. If the difference between the sensor data of the sensor A and the sensor data of the sensor B is large, the road on the side where the sensor A is located is possibly too high in bumpiness degree, or the sensor data of the sensor A is abnormal. If the sensor data of the sensor A is different from that of the sensor C on the same side greatly, the sensor data of the sensor A is proved to be abnormal, and the sensor data of the sensor A can be removed.
Therefore, abnormal sensor data can be eliminated, the accuracy of the sensor data is guaranteed, and the accuracy of jolting point detection is improved.
And S1014, after the data are cleaned, in the sensor data of the designated sensor, the deformation data corresponding to each sampling time is used as the first time series data of the designated sensor.
Wherein the specified number of sensors may be one or more.
By adopting the embodiment of the disclosure, the similarity among the sensor data of a plurality of sensors on the vehicle is calculated, one sensor is selected from the sensors with high sensor data similarity to serve as the designated sensor, the calculated amount can be reduced, and meanwhile, the sensor with low similarity serves as the designated sensor, so that the accuracy of the sensor data can be improved, and further, the accuracy of the final bump point detection is improved.
In the case where the first time-series data corresponding to the plurality of designated sensors is obtained through the flow of fig. 3, the step S103 may be specifically implemented as:
and calculating the difference value between the deformation data corresponding to each sampling moment and the deformation data predicted value based on the first time series data and the second time series data of the specified sensor for each specified sensor. And carrying out standardization processing on the plurality of calculated difference values of the designated sensors at the same sampling time to obtain a difference value corresponding to each sampling time.
In the embodiment of the present disclosure, the number of the designated sensors may be multiple, and at this time, the first time series data of each designated sensor needs to be predicted to obtain the second time series corresponding to each designated sensor.
In the embodiment of the present disclosure, each designated sensor corresponds to one difference value at the same sampling time, for example, if the number of the designated sensors is 4, each sampling time corresponds to 4 difference values, at this time, the 4 difference values corresponding to each sampling time need to be normalized to obtain one difference value, that is, each sampling time corresponds to one normalized difference value.
During subsequent difference analysis, the standard difference corresponding to each sampling moment can be analyzed, so that sensor data acquired by a plurality of designated sensors can be integrated to detect the bump point, and the accuracy of bump point detection can be improved.
In another embodiment of the present disclosure, the specified threshold in S104 may be a preset value, or may be a value obtained by analyzing a difference value corresponding to each sampling time, as shown in fig. 5, where S104 may specifically be implemented as:
and S1041, analyzing the calculated difference value corresponding to each sampling moment to obtain an appointed threshold value.
The specified threshold may be obtained by performing statistical analysis on a difference value corresponding to each sampling time, and S1041 may specifically be implemented as:
and carrying out statistical analysis on the calculated difference values corresponding to the sampling moments to obtain an average value, a standard deviation and a confidence interval, and calculating the specified threshold value based on the average value, the standard deviation and the confidence interval.
In the embodiment of the present disclosure, each sampling time corresponds to one difference, and the distribution of the plurality of differences conforms to the normal distribution, so that the average value, the standard deviation, and the confidence interval of the plurality of differences can be counted, and the corresponding difference at the right boundary of the confidence interval is used as the designated threshold.
For example, the difference at the right boundary of the 90% confidence interval may be taken as the specified threshold, and the specified threshold is the average +1.645 standard deviation.
The method for obtaining the average value, the standard deviation and the confidence interval by carrying out statistical analysis on the difference values corresponding to the sampling moments is equivalent to obtaining the distribution rules of a plurality of difference values, and the corresponding difference value at the right boundary of the confidence interval is used as the designated threshold, so that the designated threshold is prevented from being selected too large or too small, and the selection accuracy of the designated threshold is improved.
In the embodiment of the present disclosure, street view verification may be performed on a geographic coordinate on a road section to be detected at a sampling time corresponding to a difference value of a specified threshold, that is, whether a road surface at the geographic coordinate is uneven is checked through a street view function in a map APP, as shown in fig. 6a and 6b, fig. 6a and 6b are exemplary schematic diagrams of two kinds of street view verification, where a road surface in fig. 6a is uneven, and a road surface in fig. 6b is flat.
For the case in fig. 6b, if the road surface at the geographic coordinates is flat, S1041 needs to be performed again, the confidence interval is adjusted, for example, the specified threshold may be recalculated from 90% confidence interval to 95% confidence interval until it is determined that the road surface unevenness does exist by performing street view check on the specified threshold, and then it is determined that the calculated specified threshold may be used to determine the bump point.
It should be noted that there may be a plurality of sampling moments corresponding to the difference value equal to the specified threshold, and street view verification may be performed on the geographic coordinates corresponding to one or more of the sampling moments.
S1042, obtaining each target sampling moment corresponding to the difference value larger than the specified threshold value.
And S1043, taking the geographic coordinates of each target sampling moment on the road section to be detected as a bump point on the road section to be detected.
In the embodiment of the present disclosure, the obtained multiple bumpy points may be sampled, and then street view verification may be performed on the sampled bumpy points to verify the accuracy of the scheme for detecting the bumpy points, as shown in fig. 7, where fig. 7 is an exemplary schematic diagram of street view verification performed on the bumpy points with longitude and latitude of 113.286928174023 and 23.4640176275531.
In an actual service scene, the difference value of 208074 sampling moments is mined by adopting the embodiment to obtain 7804 bumpy points, the bumpy points are sampled from 7084 bumpy points to carry out street view verification, the bumpy points of the sampled parts are verified, and the accuracy rate of the bumpy point detection obtained by the scheme is estimated to be about 75%.
By adopting the embodiment of the disclosure, the second time sequence is obtained according to the prediction of the first time sequence, and the prediction error exists, so that the difference value caused by the prediction error may exist at each sampling moment, in order to accurately find the jolting point, a plurality of difference values need to be analyzed to determine the appointed threshold value, which is equivalent to find the critical value between the difference value caused by the prediction error and the difference value caused by jolting, and further, the geographic coordinate of the sampling moment of which the difference value is greater than the appointed threshold value on the road section to be detected can be used as the jolting point on the road section to be detected, so that the accuracy of detecting the jolting point is improved.
In another embodiment of the present disclosure, after the bumping points are determined, the bumping degrees of the bumping points may be further distinguished, and after the above S104, the bumping degrees of the bumping points may be further determined based on the difference values corresponding to the bumping points.
By determining the degree of jolt of each jolt point on the road section to be detected, the flatness of the road section to be detected can be determined more accurately and more intuitively, and the road condition information display of the road section to be detected is facilitated.
In the embodiment of the present disclosure, the grade division rule of the degree of jounce may be set by a technician according to an actual service scenario, and the grade division rule of the degree of jounce is not specifically limited in the embodiment of the present disclosure.
In one implementation, the degree of the jolt at the jolt point may be divided according to the magnitude of the difference, for example, a fixed value may be preset, the degree of the jolt at the jolt point corresponding to the difference greater than the fixed value is determined as a heavy jolt, and the degree of the jolt at the jolt point corresponding to the difference less than or equal to the fixed value is determined as a light jolt.
In another implementation manner, Data Exploratory Analysis (EDA) may be performed on the difference value corresponding to each bumping point to obtain a box diagram of the difference value of the bumping point, and the bumping degree is divided according to the box diagram of the difference value, as shown in fig. 8, the bumping degree of each bumping point is determined based on the difference value corresponding to each bumping point, which may specifically be implemented as:
s801, carrying out boxplot analysis on the difference values corresponding to the bumping points to obtain the statistical value of the difference values corresponding to the bumping points.
Wherein, the statistical value includes the maximum value, the minimum value, the upper quartile, the lower quartile, and may further include: mean, standard deviation, and median, etc.
S802, determining a plurality of bumpiness degree intervals based on the statistical values.
In the embodiment of the present disclosure, the bumping degree interval may be set according to an actual service scenario, and the specific manner of dividing the bumping degree interval is not specifically limited in the embodiment of the present disclosure.
For example, two jounce degree intervals may be obtained by determining [ minimum, upper quartile ] as a light jounce interval and [ upper quartile, maximum ] as a heavy jounce interval.
And determining the [ minimum value, lower quartile ] as a slight bump interval, determining the [ lower quartile, upper quartile ] as a moderate bump interval, and determining the [ upper quartile, maximum value ] as a severe bump interval to obtain three bump degree intervals.
And S803, matching the difference value corresponding to each bumping point with each bumping degree interval to obtain the bumping degree of each bumping point.
In the embodiment of the disclosure, the bumping degree of the bumping point can be determined according to the interval where the difference value corresponding to the bumping point is located.
For example, if the [ upper quartile, maximum value ] interval is a severe jounce interval, and the difference value corresponding to the jounce point a is within the [ upper quartile, maximum value ], the degree of jounce at the jounce point a is severe jounce.
By adopting the embodiment of the disclosure, the box plot analysis is carried out on the difference value corresponding to each bumping point, and different bumping degree intervals are divided, so that the accuracy of determining the bumping degree of each bumping point can be improved, and further, the bumping degree of the road section to be tested can be displayed more intuitively.
In another embodiment of the present disclosure, after determining the bump point, a bump index of the road segment to be measured may be calculated in the following manner:
and taking the ratio of the number of the bump points on the road section to be detected to the number of the deformation data included in the first time sequence data as a bump index of the road section to be detected.
It can be understood that the larger the bump index of the road section to be detected is, the higher the bump degree of the road section to be detected is, and the road section with the large bump index needs to be avoided in the driving process of the vehicle.
For example, the number of the bump points on the road segment to be measured is 100, and the first time sequence totally includes the deformation data corresponding to 500 sampling times, so that the bump index of the road segment to be measured is 100/500-0.2.
The ratio between the number of the bumping points of the road section to be detected and the number of the deformation data included in the first time sequence data is calculated to serve as the bumping index of the road section to be detected, and then the bumping degree of the road section can be judged according to the bumping index of the road section, so that the bumping degree of the road section can be visually presented to a user.
Through the calculation of the jolt degree division and the jolt index, the jolt degree estimation can be performed on the road sections to be detected according to the two dimensions of the jolt point number and the jolt degree of each jolt point, the jolt road sections can be marked, the road information of the jolt road sections of the marks can be displayed, the jolt road sections to be passed by can be prompted in advance, trucks can be helped to avoid uneven roads in time, the transportation speed is improved, and the goods loss rate is reduced.
By way of example, manhole covers on roads may cause slight bumps, small potholes, speed bumps, expansion joints and the like may cause moderate bumps, and large potholes may cause severe bumps, so as to remind drivers to slow down.
Meanwhile, the road bump point detection method provided by the embodiment of the disclosure does not depend on specific equipment for field detection, only needs to utilize the sensor which is originally assembled on the vehicle for data acquisition, does not increase extra cost, can improve the detection efficiency, and can realize the operation and detection of the road section to be detected.
In the embodiment of the present disclosure, the detection of the bumpy point is implemented by a time series anomaly detection algorithm. The time series anomaly detection algorithm is a process for detecting anomalous events or behaviors from normal time series data, namely, time series analysis is carried out on first time series data to predict to obtain second time series data, and then the difference of each sampling time between the first time series data and the second time series data is compared to determine a bump point.
Corresponding to the above method embodiment, the embodiment of the present disclosure further provides a road bump point detection device, as shown in fig. 9, the device includes:
the acquisition module 901 is configured to acquire first time series data, where the first time series data are deformation data of each sampling time acquired by a sensor in a vehicle during a driving process of the vehicle on a road section to be detected;
the prediction module 902 is configured to perform time series prediction on the first time series data to obtain second time series data, where the second time series data includes a deformation data prediction value corresponding to each sampling time of the first time series;
a calculating module 903, configured to calculate a difference between the deformation data corresponding to each sampling time and a deformation data prediction value;
and the bump point determining module 904 is configured to perform data analysis on the difference value corresponding to each sampling time calculated by the calculating module, and use the geographic coordinate corresponding to the sampling time with the difference value being greater than the specified threshold value as the bump point on the road segment to be detected.
In another embodiment of the present disclosure, the bump point determining module 904 is specifically configured to:
analyzing the calculated difference value corresponding to each sampling moment to obtain an appointed threshold value;
acquiring each target sampling moment corresponding to the difference value larger than the specified threshold value;
and taking the geographic coordinates of each target sampling moment on the road section to be detected as the bump points on the road section to be detected.
In another embodiment of the present disclosure, the bump point determining module 904 is specifically configured to:
carrying out statistical analysis on the calculated difference values corresponding to the sampling moments to obtain an average value, a standard deviation and a confidence interval;
based on the mean, standard deviation and confidence interval, a specified threshold is calculated.
In another embodiment of the present disclosure, the apparatus further comprises:
and the bumping degree determining module is used for determining the bumping degree of each bumping point based on the difference value corresponding to each bumping point.
In another embodiment of the present disclosure, the bumping degree determining module is specifically configured to:
performing boxplot analysis on the difference values corresponding to the bumping points to obtain statistical values of the difference values corresponding to the bumping points, wherein the statistical values comprise a maximum value, a minimum value, an upper quartile and a lower quartile;
determining a plurality of jounce degree intervals based on the statistical value;
and matching the difference value corresponding to each bumping point with each bumping degree interval to obtain the bumping degree of each bumping point.
In another embodiment of the present disclosure, the apparatus further comprises:
and the bump index determining module is used for taking the ratio of the number of bump points on the road section to be detected to the number of deformation data included in the first time sequence data as the bump index of the road section to be detected.
In another embodiment of the present disclosure, the obtaining module 901 is specifically configured to:
acquiring sensor data acquired by a sensor on a vehicle in the running process of the vehicle on a road section to be detected, wherein the sensor data comprises time and deformation data with a corresponding relation, and the deformation data is gravity acceleration or deformation quantity;
data cleaning is carried out on the sensor data;
and taking the deformation data corresponding to each sampling moment after the data is cleaned as first time series data.
In another embodiment of the present disclosure, the obtaining module 901 is specifically configured to:
acquiring sensor data acquired by a plurality of sensors on a vehicle in the running process of the vehicle on a road section to be detected, wherein the sensor data comprises time and deformation data with corresponding relation, and the deformation data is gravity acceleration or deformation quantity;
respectively cleaning the sensor data of each sensor;
selecting a designated sensor from the plurality of sensors based on the similarity between the sensor data of each sensor after data cleaning;
after the data are cleaned, deformation data corresponding to each sampling time in the sensor data of the designated sensor are used as first time sequence data of the designated sensor.
In another embodiment of the present disclosure, the number of sensors is specified as a plurality; the calculating module 903 is specifically configured to:
for each specified sensor, calculating a difference value between deformation data corresponding to each sampling moment and a deformation data prediction value based on first time sequence data and second time sequence data of the specified sensor;
and carrying out standardization processing on the plurality of calculated difference values of the designated sensors at the same sampling time to obtain a difference value corresponding to each sampling time.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
FIG. 10 illustrates a schematic block diagram of an example electronic device 1000 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 10, the apparatus 1000 includes a computing unit 1001 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)1002 or a computer program loaded from a storage unit 1008 into a Random Access Memory (RAM) 1003. In the RAM 1003, various programs and data necessary for the operation of the device 1000 can also be stored. The calculation unit 1001, the ROM 1002, and the RAM 1003 are connected to each other by a bus 1004. An input/output (I/O) interface 1005 is also connected to bus 1004.
A number of components in device 1000 are connected to I/O interface 1005, including: an input unit 1006 such as a keyboard, a mouse, and the like; an output unit 1007 such as various types of displays, speakers, and the like; a storage unit 1008 such as a magnetic disk, an optical disk, or the like; and a communication unit 1009 such as a network card, a modem, a wireless communication transceiver, or the like. The communication unit 1009 allows the device 1000 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel or sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.
Claims (20)
1. A road bump point detection method comprising:
acquiring first time sequence data, wherein the first time sequence data is deformation data of each sampling moment acquired by a sensor in a vehicle in the driving process of the vehicle on a road section to be detected;
performing time series prediction on the first time series data to obtain second time series data, wherein the second time series data comprise deformation data prediction values corresponding to each sampling moment of the first time series;
calculating a difference value between the deformation data corresponding to each sampling moment and a deformation data prediction value;
and performing data analysis on the calculated difference value corresponding to each sampling moment, and taking the geographic coordinate corresponding to the sampling moment with the difference value larger than the specified threshold value as a bump point on the road section to be detected.
2. The method according to claim 1, wherein the performing data analysis on the calculated difference value corresponding to each sampling time, and using the geographic coordinate corresponding to the sampling time with the difference value larger than a specified threshold value as the bump point on the road segment to be measured comprises:
analyzing the calculated difference value corresponding to each sampling moment to obtain the specified threshold value;
acquiring each target sampling moment corresponding to the difference value larger than the specified threshold value;
and taking the geographic coordinates of each target sampling moment on the road section to be detected as the bump points on the road section to be detected.
3. The method according to claim 2, wherein the analyzing the calculated difference value corresponding to each sampling time to obtain the specified threshold value comprises:
carrying out statistical analysis on the calculated difference values corresponding to the sampling moments to obtain an average value, a standard deviation and a confidence interval;
calculating the specified threshold based on the mean, the standard deviation, and the confidence interval.
4. The method according to any one of claims 1 to 3, after the performing data analysis on the calculated difference value corresponding to each sampling time, and taking the geographic coordinate corresponding to the sampling time with the difference value larger than a specified threshold value as the bump point on the road segment to be detected, the method further comprises:
and determining the bumping degree of each bumping point based on the difference value corresponding to each bumping point.
5. The method of claim 4, wherein determining a degree of jounce for each point of jounce based on the difference between the point of jounce comprises:
performing boxplot analysis on the difference values corresponding to the bumping points to obtain statistical values of the difference values corresponding to the bumping points, wherein the statistical values comprise a maximum value, a minimum value, an upper quartile and a lower quartile;
determining a plurality of jounce degree intervals based on the statistical value;
and matching the difference value corresponding to each bumping point with each bumping degree interval to obtain the bumping degree of each bumping point.
6. The method according to claim 1, wherein after the data analysis is performed on the calculated difference value corresponding to each sampling time, and the geographic coordinate corresponding to the sampling time with the difference value larger than a specified threshold value is used as the bump point on the road segment to be measured, the method further comprises:
and taking the ratio of the number of the bump points on the road section to be detected to the number of the deformation data included in the first time sequence data as a bump index of the road section to be detected.
7. The method of claim 1, wherein the obtaining first time-series data comprises:
acquiring sensor data acquired by a sensor on the vehicle in the running process of the vehicle on the road section to be detected, wherein the sensor data comprises time and deformation data with a corresponding relation, and the deformation data is gravity acceleration or deformation quantity;
performing data cleaning on the sensor data;
and taking the deformation data corresponding to each sampling moment after data cleaning as the first time sequence data.
8. The method of claim 1, wherein the obtaining first time-series data comprises:
acquiring sensor data acquired by a plurality of sensors on the vehicle in the running process of the vehicle on the road section to be detected, wherein the sensor data comprises time and deformation data with corresponding relation, and the deformation data is gravity acceleration or deformation quantity;
respectively cleaning the sensor data of each sensor;
selecting a designated sensor from the plurality of sensors based on the similarity between the sensor data of each sensor after data cleaning;
after data is cleaned, deformation data corresponding to each sampling moment in the sensor data of the specified sensor is used as first time sequence data of the specified sensor.
9. The method of claim 8, wherein the designated sensor is plural in number; the calculating the difference value between the deformation data corresponding to each sampling moment and the deformation data prediction value comprises the following steps:
for each specified sensor, calculating a difference value between deformation data corresponding to each sampling moment and a deformation data prediction value based on first time sequence data and second time sequence data of the specified sensor;
and carrying out standardization processing on a plurality of calculated difference values of each specified sensor at the same sampling moment to obtain a difference value corresponding to each sampling moment.
10. A road bump point detection device comprising:
the acquisition module is used for acquiring first time sequence data, wherein the first time sequence data are deformation data of each sampling moment acquired by a sensor in a vehicle in the driving process of the vehicle on a road section to be detected;
the prediction module is used for predicting the time sequence of the first time sequence data to obtain second time sequence data, and the second time sequence data comprises a deformation data prediction value corresponding to each sampling moment of the first time sequence;
the calculation module is used for calculating the difference value between the deformation data corresponding to each sampling moment and the deformation data prediction value;
and the bump point determining module is used for carrying out data analysis on the calculated difference value corresponding to each sampling moment, and taking the geographic coordinate corresponding to the sampling moment with the difference value larger than the specified threshold value as the bump point on the road section to be detected.
11. The apparatus of claim 10, wherein the bump point determining module is specifically configured to:
analyzing the calculated difference value corresponding to each sampling moment to obtain the specified threshold value;
acquiring each target sampling moment corresponding to the difference value larger than the specified threshold value;
and taking the geographic coordinates of each target sampling moment on the road section to be detected as the bump points on the road section to be detected.
12. The apparatus of claim 11, wherein the bump point determination module is specifically configured to:
carrying out statistical analysis on the calculated difference values corresponding to the sampling moments to obtain an average value, a standard deviation and a confidence interval;
calculating the specified threshold based on the mean, the standard deviation, and the confidence interval.
13. The apparatus of any of claims 10-12, further comprising:
and the bumping degree determining module is used for determining the bumping degree of each bumping point based on the difference value corresponding to each bumping point.
14. The apparatus of claim 13, wherein the jounce level determining module is specifically configured to:
performing boxplot analysis on the difference values corresponding to the bumping points to obtain statistical values of the difference values corresponding to the bumping points, wherein the statistical values comprise a maximum value, a minimum value, an upper quartile and a lower quartile;
determining a plurality of jounce degree intervals based on the statistical value;
and matching the difference value corresponding to each bumping point with each bumping degree interval to obtain the bumping degree of each bumping point.
15. The apparatus of claim 10, wherein the apparatus further comprises:
and the bump index determining module is used for taking the ratio of the number of bump points on the road section to be detected to the number of deformation data included in the first time sequence data as the bump index of the road section to be detected.
16. The apparatus according to claim 10, wherein the obtaining module is specifically configured to:
acquiring sensor data acquired by a sensor on the vehicle in the running process of the vehicle on the road section to be detected, wherein the sensor data comprises time and deformation data with a corresponding relation, and the deformation data is gravity acceleration or deformation quantity;
performing data cleaning on the sensor data;
and taking the deformation data corresponding to each sampling moment after data cleaning as the first time sequence data.
17. The apparatus according to claim 10, wherein the obtaining module is specifically configured to:
acquiring sensor data acquired by a plurality of sensors on the vehicle in the running process of the vehicle on the road section to be detected, wherein the sensor data comprises time and deformation data with corresponding relation, and the deformation data is gravity acceleration or deformation quantity;
respectively cleaning the sensor data of each sensor;
selecting a designated sensor from the plurality of sensors based on the similarity between the sensor data of each sensor after data cleaning;
after data is cleaned, deformation data corresponding to each sampling time in the sensor data of the specified sensor is used as first time sequence data of the specified sensor.
18. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.
19. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-9.
20. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210297104.8A CN114676175A (en) | 2022-03-24 | 2022-03-24 | Road bump point detection method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210297104.8A CN114676175A (en) | 2022-03-24 | 2022-03-24 | Road bump point detection method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114676175A true CN114676175A (en) | 2022-06-28 |
Family
ID=82073950
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210297104.8A Pending CN114676175A (en) | 2022-03-24 | 2022-03-24 | Road bump point detection method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114676175A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115685932A (en) * | 2022-10-31 | 2023-02-03 | 青岛家哇云网络科技有限公司 | Logistics information intelligent management system and method based on big data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103669183A (en) * | 2013-12-02 | 2014-03-26 | 黑龙江科技大学 | Time sequence model of road surface evenness |
| US20140163770A1 (en) * | 2011-07-20 | 2014-06-12 | Bridgestone Corporation | Road surface condition estimating method, and road surface condition estimating apparatus |
| JP2019001367A (en) * | 2017-06-16 | 2019-01-10 | 株式会社ブリヂストン | Road state discrimination method and road state discrimination device |
| CN110852542A (en) * | 2018-08-21 | 2020-02-28 | 上海汽车集团股份有限公司 | Road flatness calculation method and system |
| CN111627237A (en) * | 2020-05-21 | 2020-09-04 | 北京骑胜科技有限公司 | Road condition detection method, road condition detection device, server and computer readable storage medium |
-
2022
- 2022-03-24 CN CN202210297104.8A patent/CN114676175A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140163770A1 (en) * | 2011-07-20 | 2014-06-12 | Bridgestone Corporation | Road surface condition estimating method, and road surface condition estimating apparatus |
| CN103669183A (en) * | 2013-12-02 | 2014-03-26 | 黑龙江科技大学 | Time sequence model of road surface evenness |
| JP2019001367A (en) * | 2017-06-16 | 2019-01-10 | 株式会社ブリヂストン | Road state discrimination method and road state discrimination device |
| CN110852542A (en) * | 2018-08-21 | 2020-02-28 | 上海汽车集团股份有限公司 | Road flatness calculation method and system |
| CN111627237A (en) * | 2020-05-21 | 2020-09-04 | 北京骑胜科技有限公司 | Road condition detection method, road condition detection device, server and computer readable storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 刘庆华;张为公;李忠国;: "基于路面垂直动载自回归建模的IRI测量方法", 东南大学学报(自然科学版), no. 06, 20 November 2007 (2007-11-20) * |
| 王佳秋;邓慧;王葳;马松林;: "应用路面平整度预测的数学模型促进黑龙江省高速公路建设", 经济研究导刊, no. 11, 15 April 2016 (2016-04-15) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115685932A (en) * | 2022-10-31 | 2023-02-03 | 青岛家哇云网络科技有限公司 | Logistics information intelligent management system and method based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11579307B2 (en) | Method and apparatus for detecting obstacle | |
| US9824580B2 (en) | Method, computer readable storage medium and system for producing an uncertainty-based traffic congestion index | |
| CN113593218B (en) | Method and device for detecting traffic abnormal event, electronic equipment and storage medium | |
| CN110689804B (en) | Method and apparatus for outputting information | |
| CN112579464A (en) | Verification method, device and equipment of automatic driving algorithm and storage medium | |
| CN114120650B (en) | Method and device for generating test results | |
| CN112526999A (en) | Speed planning method, device, electronic equipment and storage medium | |
| CN113066302A (en) | Vehicle information prediction method and device and electronic equipment | |
| CN114676175A (en) | Road bump point detection method, device, equipment and medium | |
| CN110186472B (en) | Vehicle yaw detection method, computer device, storage medium, and vehicle system | |
| CN114677848A (en) | Perception early warning system, method, device and computer program product | |
| CN114625744A (en) | Updating method and device of electronic map | |
| CN111352142A (en) | Indoor parking positioning method and device, electronic equipment and medium | |
| US11417114B2 (en) | Method and apparatus for processing information | |
| CN112651535A (en) | Local path planning method and device, storage medium, electronic equipment and vehicle | |
| CN113284337B (en) | OD matrix calculation method and device based on vehicle track multidimensional data | |
| KR20200074758A (en) | System providing prediction information for quantity of parked vehicle and congestion degree of parking using analysing of access vehicle in parking lot | |
| CN113380046B (en) | Method and device for identifying vehicle driving state based on fixed line and electronic equipment | |
| WO2018019144A1 (en) | Navigation object determining method and apparatus | |
| CN115206102A (en) | Method, apparatus, electronic device, and medium for determining traffic path | |
| CN114104046A (en) | Method, device and equipment for judging idle sliding of train and computer readable storage medium | |
| JP2018180906A (en) | Congestion prediction program, congestion prediction apparatus, and congestion prediction method | |
| CN114166234A (en) | System, method, device, processor and computer storage medium for selecting navigation route and road damage identification early warning based on road damage measurement | |
| CN113052397A (en) | Method and device for determining getting-on information, electronic equipment and storage medium | |
| CN113470343A (en) | Road blocking opening detection method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |